AIforCOVID: Predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. An Italian multicentre study.

Recent epidemiological data report that worldwide more than 53 million people have been infected by SARS-CoV-2, resulting in 1.3 million deaths. The disease has been spreading very rapidly and few months after the identification of the first infected, shortage of hospital resources quickly became a problem. In this work we investigate whether artificial intelligence working with chest X-ray (CXR) scans and clinical data can be used as a possible tool for the early identification of patients at risk of severe outcome, like intensive care or death. Indeed, further to induce lower radiation dose than computed tomography (CT), CXR is a simpler and faster radiological technique, being also more widespread. In this respect, we present three approaches that use features extracted from CXR images, either handcrafted or automatically learnt by convolutional neuronal networks, which are then integrated with the clinical data. As a further contribution, this work introduces a repository that collects data from 820 patients enrolled in six Italian hospitals in spring 2020 during the first COVID-19 emergency. The dataset includes CXR images, several clinical attributes and clinical outcomes. Exhaustive evaluation shows promising performance both in 10-fold and leave-one-centre-out cross-validation, suggesting that clinical data and images have the potential to provide useful information for the management of patients and hospital resources.

Machine Learning to Predict In-Hospital Mortality in COVID-19 Patients Using Computed Tomography-Derived Pulmonary and Vascular Features.

Pulmonary parenchymal and vascular damage are frequently reported in COVID-19 patients and can be assessed with unenhanced chest computed tomography (CT), widely used as a triaging exam. Integrating clinical data, chest CT features, and CT-derived vascular metrics, we aimed to build a predictive model of in-hospital mortality using univariate analysis (Mann-Whitney U test) and machine learning models (support vectors machines (SVM) and multilayer perceptrons (MLP)). Patients with RT-PCR-confirmed SARS-CoV-2 infection and unenhanced chest CT performed on emergency department admission were included after retrieving their outcome (discharge or death), with an 85/15% training/test dataset split. Out of 897 patients, the 229 (26%) patients who died during hospitalization had higher median pulmonary artery diameter (29.0 mm) than patients who survived (27.0 mm, p < 0.001) and higher median ascending aortic diameter (36.6 mm versus 34.0 mm, p < 0.001). SVM and MLP best models considered the same ten input features, yielding a 0.747 (precision 0.522, recall 0.800) and 0.844 (precision 0.680, recall 0.567) area under the curve, respectively. In this model integrating clinical and radiological data, pulmonary artery diameter was the third most important predictor after age and parenchymal involvement extent, contributing to reliable in-hospital mortality prediction, highlighting the value of vascular metrics in improving patient stratification.

Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia.

We assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia.

Pulmonary thromboembolism in hospitalised COVID-19 patients at moderate to high risk by Wells score: a report from Lombardy, Italy.

OBJECTIVES: To present a single-centre experience on CT pulmonary angiography (CTPA) for the assessment of hospitalised COVID-19 patients with moderate-to-high risk of pulmonary thromboembolism (PTE). METHODS: We analysed consecutive COVID-19 patients (RT-PCR confirmed) undergoing CTPA in March 2020 for PTE clinical suspicion. Clinical data were retrieved. Two experienced radiologists reviewed CTPAs to assess pulmonary parenchyma and vascular findings. RESULTS: Among 34 patients who underwent CTPA, 26 had PTE (76%, 20 males, median age 61 years, interquartile range 54-70), 20/26 (77%) with comorbidities (mainly hypertension, 44%), and 8 (31%) subsequently dying. Eight PTE patients were under thromboprophylaxis with low-molecular-weight heparin, four PTE patients had lower-limbs deep vein thrombosis at ultrasound examination (performed in 33/34 patients). Bilateral PTE characterised 19/26 cases, with main branches involved in 10/26 cases. Twelve patients had a parenchymal involvement >75%, the predominant pneumonia pattern being consolidation in 10/26 patients, ground glass opacities in 9/26, crazy paving in 5/26, and both ground glass opacities and consolidation in 2/26. CONCLUSION: COVID-19 patients are prone to PTE. ADVANCES IN KNOWLEDGE: PTE, potentially attributable to an underlying thrombophilic status, may be more frequent than expected in COVID-19 patients. Extension of prophylaxis and adaptation of diagnostic criteria should be considered.

CT-derived pulmonary vascular metrics and clinical outcome in COVID-19 patients.

To assess pulmonary vascular metrics on chest CT of COVID-19 patients, and their correlation with pneumonia extent (PnE) and outcome, we analyzed COVID-19 patients with an available previous chest CT, excluding those performed for cardiovascular disease. From February 21 to March 21, 2020, of 672 suspected COVID-19 patients from two centers who underwent CT, 45 RT-PCR-positives (28 males, median age 75, IQR 66-81 years) with previous CTs performed a median 36 months before (IQR 12-72 months) were included. We assessed PnE, pulmonary artery (PA) diameter, ascending aorta (Ao) diameter, and PA/Ao ratio. Most common presentations were fever and dyspnea (15/45) and fever alone (13/45). Outcome was available for 41/45 patients, 15/41 dead and 26/41 discharged. Ground-glass opacities (GGOs) alone were found in 29/45 patients, GGOs with consolidations in 15/45, consolidations alone in 1/45. All but one patient had bilateral pneumonia, 9/45 minimal, 22/45 mild, 9/45 moderate, and 5/45 severe PnE. PA diameter (median 31 mm, IQR 28-33 mm) was larger than before (26 mm, IQR 25-29 mm) (P<0.001), PA/Ao ratio (median 0.83, IQR 0.76-0.92) was higher than before (0.76, IQR 0.72-0.82) (P<0.001). Patients with adverse outcome (death) had higher PA diameter (P=0.001), compared to discharged ones. Only weak correlations were found between ΔPA or ΔPA/Ao and PnE (ρ≤0.453, P≤0.032), with 4/45 cases with moderate-severe PnE and minimal increase in PA metrics. In conclusion, enlarged PA diameter was associated to death in COVID-19 patients, a finding deserving further investigation as a potential driver of therapy decision-making.